AI gateway · FinOps · Governance

The AI gateway for every model, every cost, every team

One OpenAI-compatible API to around 1,000 models for your developers, the cost of every request for finance, and budgets, roles and model access per team for your admins.

Get your API key

Talk to us

Or email us at [email protected]

No subscription · Provider prices, no markup · 5.5% fee only when you buy credits

Made in the EUSOC 2 & ISO 27001 CERTIFIED • ZERO DATA RETENTION

Trusted by developers building AI in production.

AI models

~1000

Providers

50+

Developers

300k+

Uptime

99.99%

Trusted by Global Companies

One console

See every model, every cost and every rule on one screen

The same dashboard serves developers, finance and admins: which models answered, what each team spent, and which budgets and rules apply.

Eden AI · Overview

Platform

Models

Overview

API keys

Routing

Organization

Members

Guardrails

Billing

Requests

1.92M

+12% vs. last month

Spend

$4,128

−39% vs. direct provider prices

Attributed spend

93%

7% untagged · review

Uptime

99.99%

fallbacks used 142 times

Gateway · last requests

gpt-6-luna

azure

$0.000081

claude-sonnet-5-5

anthropic

$0.0027

mistral-large-4

fallback

billed once

ocr/invoice

mindee

$0.010

FinOps · spend by team

Customer support

$1,912

Data science

$1,240

Marketing

$703

Untagged

$273

Governance · budgets & rules

Customer support

82%

Marketing

paused

allowmistral/*openai/*@eu

deny*/*EU only

Data stays in Europe

https://api.eu.edenai.run/v3

Same API. Non-EU models are refused, never billed.

Saved this month

$2,640

routing · cache · fallbacks

Three questions, one API key

What are your teams calling, what does it cost, and who decides?

Most companies can answer one of the three. A gateway answers the first, spreadsheets guess at the second, and nobody owns the third. Eden AI answers all three from one place.

AI gateway & LLM router

One OpenAI-compatible API to around 1,000 LLMs and expert models across 50+ providers, with smart routing, fallbacks and a dedicated EU endpoint.

Model	Region	$ / M in
gpt-6-luna	EU	$0.12
claude-sonnet-5-5	US	$2.00
mistral-large-4	EU	$0.68
ocr/invoice	EU	$0.01 / page

One key, one request shape, ~1000 models

Browse models

AI FinOps

LLM cost optimization built in: cost-based routing, caching, fallbacks billed once and the cost of every request in the response. Track and cap spend per team, or per product and end user for the AI products you ship. Up to 40% lower token spend, without changing your code.

Spend

$4,128

−39% vs. direct

Saved

$2,640

this month

Cheaper providers

$1,694

Response cache

$563

Prompt caching

$292

Fallbacks billed once

$91

Cut token costs by up to 40%

AI governance

Tags on every call, budgets per key, model allow-lists, roles, SSO and audit logs.

Client	Cost	Share
acme	$1,912	46%
globex	$1,240	30%
initech	$703	17%
Untagged	$273	7%

Budget · acme-prod

64%

Explore organization management

Made in the EU

Made in Europe, ready for procurement

The questions security and legal ask, answered before they ask them. Eden AI is a French company. Keep requests in Europe with the EU endpoint, retain nothing by default, and give your security team the certifications and the DPA they expect.

Made in the EU

A French company based in Lyon.

Certified

SOC 2ISO 27001GDPR-ready

Security documentation and a Data Processing Agreement for procurement reviews.

EU endpoint

https://api.eu.edenai.run/v3

EUSame API, dedicated European routing

451Non-EU models are refused and never billed

Data handling

Zero Data Retention by default

No training on customer data

Log retention (opt-in)

Pricing

Provider prices, one transparent fee

Pay each provider's exact price from prepaid credits. The only fee is shown upfront, and larger organizations can move to custom terms.

Markup on provider prices

The model catalog shows each provider's exact price.

Platform fee

5.5%

Applied only when you buy credits. Nothing per request.

Subscription

Pay as you go. No API call limit.

Advanced plan

Custom

Volume discounts, SSO, SCIM, audit logs and custom billing.

See pricing

Talk to us

Built for production

Everything between your app and the models

01 · Gateway

One API, every model, your rules

Point the OpenAI or Anthropic SDK at Eden AI and reach every major LLM plus expert models for OCR, speech, vision and translation. Sort providers by cost, speed or latency, restrict them to the ones you approve, pin traffic to Europe and declare fallbacks.

Browse models

Read the docs

Routing strategy · prod-support

Sort providers by

costspeedlatencyexact

Allowed providers

openaiazuremistraldeepinfra+ add

Allow fallbacks

Sticky routing per conversation

Region

Any regionEU only · @eu

Fallback models

mistral/mistral-small-latestgoogle/gemini-3.8-flash

Save routing strategyPreview cost impact

Monitoring · Spend by product and end user

Spend

$4,128

−39% vs. direct prices

Cost per request

$0.0019

vs. $0.0110 single model

Cache hits

23%

441k requests at $0.00

Spend by product · budget per API key

Product	Cost	Budget
product=support-assistant	$1,912
product=doc-search	$1,240
product=invoice-parser	$703

Top end users · support-assistant

End user	Requests	Cost	Cap
user=cust_8f2a	41,200	$96.40	$150 / mo
user=cust_19c4	28,950	$71.10	$150 / mo
user=cust_a07e	22,310	$149.80	cap reached

02 · FinOps

Pay less per request, and see every cent

Cost-based routing sends each request to the cheapest capable provider, repeated requests are served from cache at no cost, failed attempts are never billed, and every response carries its cost in USD. Control spend per team inside your company, or per product and end user for the AI features you sell: tag each request, give each product or customer its own API key and budget, and see who drives the bill.

Cut token costs by up to 40%

See pricing

03 · Governance

Every token attributed, every team inside its budget

Tag requests with the client, project or team they belong to, and see what each one spends. Give each API key a budget that resets daily, weekly or monthly, and decide which models each role may call.

Explore organization management

Talk to us

Monitoring · Usage by client

Sep 1Sep 15Sep 30

acmeglobexinitech

Client	Requests	Cost
acme	812,400	$1,912
globex	540,112	$1,240
initech	301,870	$703

04 · Expert models

Go beyond generic LLMs

When a general-purpose LLM is not the best fit, Eden AI gives you access to expert models built for document parsing, speech, vision, translation and more, through the same key and the same monitoring.

Browse AI features

Browse providers

Our Customer Stories

I believe in accessing AI services through a one-stop shop that brings together major providers like Amazon and Azure, as well as emerging specialists. Eden AI is the right solution for our first ‘laboratory’ stage, giving us a portal with multiple services we can use depending on each project.

Alain Mielle

Innovation Manager @Council of Europe

We chose Eden AI not only because it's a French company, which matters to us in a local partnership mindset, but also because their APIs are powerful, well-documented, and offer great technical flexibility.

Julien Cyr

CEO @Holberton School

We were impressed by the vast amount of functions available from Eden AI, which covered almost all of our current and planned user cases. The flexibility and advanced technology Eden AI offers have been essential in helping us improve the efficiency of our College Admissions and recruitment systems.

Coong Cooc

Systems Development Senior Manager @UWCSEA

We use Eden AI because of its standard interface that connects into various AI providers, so we can test & compare the accuracy and manage vendor risks down the road.

Jan Vosecky

Head of Product @Re-Hub

We use Eden AI's API for seamless and easy integration via Make.com. It allows us to effortlessly incorporate AI-powered features into our workflows.

Fabian Konda

Managing Director @Profor Software

We are implementing a combination of sentiment analysis and topic extraction into our platform, which handles a big load of patient comments coming through a survey. It would be a hassle to setup an infrastructure to compare all the AI providers and their output, so that's why we decided for Eden AI, along with the fact that it provides us with an unified billing as opposed to maintaining an account on each of the providers.

Nikola Komes

CEO @InsiderCX

Integrate in a minute

Switch the base URL, keep your code

Eden AI is OpenAI-compatible. Routing and fallbacks are fields on the request, and the response tells you which provider answered and what it cost.

PYTHON · OPENAI SDK

# pip install openai
from openai import OpenAI

client = OpenAI(
    base_url="https://api.edenai.run/v3",
    api_key=EDENAI_API_KEY,
)

response = client.chat.completions.create(
    model="gpt-6-luna",         # no provider prefix: Eden AI picks the provider
    messages=[{"role": "user", "content": "Summarize this ticket: ..."}],
    extra_body={
        "routing": {"sort": "cost", "allow_fallbacks": True},
        "fallbacks": ["mistral/mistral-small-latest"],
    },
)
print(response.choices[0].message.content)

RESPONSE · COST INCLUDED

{
  "id": "chatcmpl-EZI7…",
  "provider": "azure",   // the provider that served the request
  "choices": [
    { "message": { "role": "assistant", "content": "Acme (Pro) reports…" } }
  ],
  "usage": {
    "prompt_tokens": 399,
    "completion_tokens": 83,
    "total_tokens": 482
  },
  "cost": 0.0000814                   // USD, on every response
}

Questions we're usually asked

Get your API key

Read the docs

What is Eden AI?

An AI gateway and LLM router: one API key and one request shape for around 1,000 LLMs and expert models across 50+ providers, with routing, fallbacks, caching, cost monitoring and organization governance built in.

Is it compatible with the OpenAI SDK?

Yes. Point the OpenAI SDK at https://api.edenai.run/v3 and keep your code. An Anthropic-compatible messages endpoint is available too.

How does pricing work?

You pay the providers' exact prices from prepaid credits, with no markup. The only additional cost is a 5.5% platform fee when you buy credits. No subscription and no API call limit. The Advanced plan adds volume discounts and custom billing.

Where is my data processed?

Eden AI is a French company. With the EU endpoint, requests are routed to European provider regions and non-EU models are refused with HTTP 451. Eden AI stores no prompts or outputs by default and never trains on your data.

Can I control spend per team, product or end user?

Yes. Tags attribute every request to a team, client, product or end user, and spend can be grouped by any of them. Each API key can carry a budget that resets daily, weekly or monthly, so a team, a product or one of your customers can have its own key and cap. Guardrails add model allow-lists, rate limits and spend caps per role, member or key.

Which plan do I need?

Start self-serve with pay-as-you-go credits. The Advanced plan adds custom routing, volume discounts, SSO, SCIM, audit logs and custom billing for larger organizations.

let’s start

Start building with Eden AI

One API for every model, with the cost control and governance your company needs.

Get your API key

Talk to us

Or email us at [email protected]

MADE IN THE EU • ZERO DATA RETENTION • SOC 2 & ISO 27001 CERTIFIED